SavedAdd your journal

Journals / Gazi University Journal of Science / 2026 / Volume: 39 Issue: 1

Forecasting Performance Comparison: LSTM Model vs. Dynamic and Static Forecasting of ARIMA and Random Walk Models - Evidence from S&P500

Levent Gül(Ankara Hacı Bayram Veli Üniversitesi)0000-0003-2517-2207
Ebru Yüksel Haliloğlu(GAZİ ÜNİVERSİTESİ)0000-0001-8267-0339
Nurhan Hande Sevgi(UFUK ÜNİVERSİTESİ)0000-0003-2347-5503
Nükhet Doğan(ANKARA HACI BAYRAM VELİ ÜNİVERSİTESİ)0000-0002-2115-1807
Hakan Berument(BİLKENT ÜNİVERSİTESİ)0000-0003-2276-4741
Pages
—
Publication Date
2026-01-30
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

The empirical evidence presented here suggests that the reported superiority of LSTM in financial time series forecasting might be due to the forecasting method that is employed rather than a genuine predictive advantage.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:This paper re-evaluates the forecasting performance of Long Short-Term Memory (LSTM) models against traditional Autoregressive Integrated Moving Average (ARIMA) and Random Walk (RW) models using S&P 500 index data.
📊
Key Findings & Data:The LSTM models in the literature, which utilize observed lagged values for their forecasting (static forecasting), are compared to traditional models that use recursive, self-generated predictions for forecasting (dynamic forecasting).
💡
Conclusion & Impact:The empirical evidence presented here suggests that the reported superiority of LSTM in financial time series forecasting might be due to the forecasting method that is employed rather than a genuine predictive advantage.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Autoregressive Integrated Moving Average · Cross-validation · Long Short-Term Memory

Abstract

This paper re-evaluates the forecasting performance of Long Short-Term Memory (LSTM) models against traditional Autoregressive Integrated Moving Average (ARIMA) and Random Walk (RW) models using S&P 500 index data. The LSTM models in the literature, which utilize observed lagged values for their forecasting (static forecasting), are compared to traditional models that use recursive, self-generated predictions for forecasting (dynamic forecasting). To provide comparable statistics, we gather relevant statistics for the static forecasting of ARIMA and RW models. We repeat the exercise for three different cross-validation schemes. The empirical evidence presented here suggests that the static forecasting power of static ARIMA and RW models consistently matches or outperforms that of LSTMs. Moreover, we find that while traditional models remain robust across varying sample sizes, the performance of LSTMs decreases when the training datasets are reduced. The empirical evidence presented here suggests that the reported superiority of LSTM in financial time series forecasting might be due to the forecasting method that is employed rather than a genuine predictive advantage.

🔖

Cite This Article

Gül, L., Haliloğlu, E. Y., Sevgi, N. H., Doğan, N., Berument, H. (2026). Forecasting Performance Comparison: LSTM Model vs. Dynamic and Static Forecasting of ARIMA and Random Walk Models - Evidence from S&P500. Gazi University Journal of Science, Volume: 39 Issue: 1. https://doi.org/10.35378/gujs.1709484

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (67)

  1. Box, G. E. P., Jenkins, G. M., Reinsel, G. C., Ljung, G. M., “Time Series Analysis: Forecasting and Control”, John Wiley and Sons, (2015).
  2. Hamilton, J. D., “Time Series Analysis”, Princeton University Press, (1994).
  3. Deboeck, G. J., “Trading on the Edge: Neural, Genetic, and Fuzzy Systems for Chaotic Financial Markets”, (39), John Wiley and Sons, (1994).
  4. Abu-Mostafa, Y. S., Atiya, A. F., “Introduction to financial forecasting”, Applied Intelligence, 6, 205-213, (1996).
  5. Schmidhuber, J., “Deep learning in neural networks: An overview”, Neural Networks, 61, 85-117, (2015).
  6. Jothi, L. S., “Time Series Analysis Using LSTM Networks and Its Application to Financial Forecasting”, In Artificial Intelligence for Financial Risk Management and Analysis, 19-58, IGI Global Scientific Publishing, (2025).
  7. Hochreiter S., Schmidhuber J., “Long Short-Term Memory”, Neural Computation MIT-Press, 9(8), 1735-1780, (1997).
  8. Roondiwala, M., Patel, H., Varma, S., “Predicting stock prices using LSTM”, International Journal of Science and Research (IJSR), 6(4), 1754-1756, (2017).
  9. Mendes, J. F. B., “Forecasting bitcoin prices: ARIMA vs LSTM”, Master’s thesis, (2019).
  10. Han, Z., Zhu, X., Su, Z., “Forecasting maritime and financial market trends: Leveraging CNN-LSTM models for sustainable shipping and China’s financial market integration”, Sustainability, 16(22), 9853, (2024).
  11. You, Y., “Forecasting stock price: A deep learning approach with LSTM and hyperparameter optimization”, Highlights Sci. Eng. Technol, 85, 328-338, (2024).
  12. Wang, J., Hong, S., Dong, Y., Li, Z., Hu, J., “Predicting stock market trends using LSTM networks: overcoming RNN limitations for improved financial forecasting”, Journal of Computer Science and Software Applications, 4(3), 1-7, (2024).
  13. Wang, Y., Zhang, H., Huang, B., Lin, Z., Pang, C., “LSTM stock prediction model based on blockchain”, High-Confidence Computing, 100316, (2025).
  14. Xiao D., Ketcha M.D., “Deep Speech 2: End-to-end speech recognition in English and mandarin”, Journal of Heterocyclic Chemistry, 32(2), 499–503, (1995).
  15. Hannun, A., Case, C., Casper, J., Catanzaro, B., Diamos, G., Elsen, E., Prenger, R., Satheesh, S., Sengupta, S., Coates, A., Andrew Y. N., “Deep Speech: Scaling up end-to-end speech recognition”, ArXiv Preprint ArXiv:1412.5567, (2014).
  16. Huang, Y., Wang, W., Wang, L., “Instance-aware image and sentence matching with selective multimodal LSTM”, In Proceedings of the IEEE conference on computer vision and pattern recognition, 2310-2318, (2017).
  17. Zhao, A., Qi, L., Dong, J., Yu, H., “Dual channel LSTM based multi-feature extraction in gait for diagnosis of neurodegenerative diseases.”, Knowledge-Based Systems, 145, 91-97, (2018).
  18. Shewalkar, A., “Performance evaluation of deep neural networks applied to speech recognition: RNN, LSTM and GRU”, Journal of Artificial Intelligence and Soft Computing Research, 9, (2019).
  19. Tatsunami, Y., Taki, M., “Sequencer: Deep LSTM for image classification”, Advances in neural information processing systems, 35, 38204-38217, (2022).
  20. Vidya, B., Sasikumar, P., “Parkinson’s disease diagnosis and stage prediction based on gait signal analysis using EMD and CNN–LSTM network”, Engineering Applications of Artificial Intelligence, 114, 105099, (2022).
  21. Hassanzadeh, H., Qadir, J. A., Omer, S. M., Ahmed, M. H., Khezri, E., “Deep learning for speaker recognition: A comparative analysis of 1D-CNN and LSTM models using diverse datasets”, In 2024 4th Interdisciplinary conference on electrics and computer (INTCEC), 1-8, IEEE, (2024).
  22. Khartheesvar, G., Kumar, M., Yadav, A. K., Yadav, D., “Automatic Indian sign language recognition using Media Pipe holistic and LSTM network”, Multimedia Tools and Applications, 83(20), 58329-58348, (2024).
  23. Wang, X., Huang, J., Chatzakou, M., Medijainen, K., Toomela, A., Nõmm, S., Ruzhansky, M., “LSTM-CNN: An efficient diagnostic network for Parkinson's disease utilizing dynamic handwriting analysis”, Computer Methods and Programs in Biomedicine, 247, 108066, (2024).
  24. Basha, S. A. K., Vincent, P. D. R., Mohammad, S. I., Vasudevan, A., Soon, E. E. H., Shambour, Q., Alshurideh, M. T., “Exploring deep learning methods for audio speech emotion detection: An ensemble MFCCs, CNNs and LSTM”, Appl. Math, 19(1), 75-85, (2025).
  25. Haq, E. U., Yong, Q., Yuan, Z., Huarong, X., Haq, R. U., “Multimodal fusion diagnosis of the Alzheimer’s disease via lightweight CNN-LSTM model using magnetic resonance imaging (MRI)”, Biomedical Signal Processing and Control, 104, 107545, (2025).
  26. Liu, Y., Brezzi, L., Liang, Z., Gabrieli, F., Zhou, Z., Cola, S., “Image analysis and LSTM methods for forecasting surficial displacements of a landslide triggered by snowfall and rainfall”, Landslides, 22(3), 619-635, (2025).
  27. Han, J. H., “Comparing models for time series analysis”, Wharton Research Scholars, Philadelphia, (2018).
  28. Yamak, P. T., Yujian, L., Gadosey, P. K., “A Comparison Between ARIMA, LSTM, and GRU for Time Series Forecasting”, In Proceedings of the 2019 2nd International Conference on Algorithms, Computing and Artificial Intelligence, 49-55, (2019).
  29. Andréasson, D., Mortensen, B. J., “Forecasting the OMXS30 - a comparison between ARIMA and LSTM”, bachelor’s Thesis, Uppsala University, (2020).
  30. Liu, X., Lin, Z., Feng, Z., “Short-term offshore wind speed forecast by seasonal ARIMA-A comparison against GRU and LSTM”, Energy, 227, 120492, (2021).
  31. Zhang, R., Song, H., Chen, Q., Wang, Y., Wang, S., Li, Y., “Comparison of ARIMA and LSTM for prediction of hemorrhagic fever at different time scales in China”, Plos One, 17(1), e0262009, (2022).
  32. Kobiela, D., Krefta, D., Król, W., Weichbroth, P., “ARIMA vs LSTM on NASDAQ stock exchange data”, Procedia Computer Science, 207, 3836-3845, (2022).
  33. Albeladi, K., Zafar, B., Mueen, A., “Time series forecasting using LSTM and ARIMA”, International Journal of Advanced Computer Science and Applications, 14(1), 313-320, (2023).
  34. Azani, N. W., Trisya, C. P., Sari, L. M., Handayani, H., Alhamid, M. R. M., “Performance Comparison of ARIMA, LSTM and SVM Models for Electric Energy Consumption Analysis”, Public Research Journal of Engineering, Data Technology and Computer Science, 1(2), (2024).
  35. Siami-Namini, S., Tavakoli, N., Namin, A. S., “A Comparison of ARIMA and LSTM in Forecasting Time Series”, 17th IEEE International Conference on Machine Learning and Applications (ICMLA), Orlando, FL, USA, (2018).
  36. Masum, S., Liu, Y., Chiverton, J., “Multi-step Time Series Forecasting of Electric Load Using Machine Learning Models”, In Artificial Intelligence and Soft Computing: 17th International Conference, Zakopane, Poland, (2018).
  37. Karakoyun, E. S., Cibikdiken, A. O., “Comparison of ARIMA Time Series Model and LSTM Deep Learning Algorithm for Bitcoin Price Forecasting”, In The 13th Multidisciplinary Academic Conference, Prague. 171-180, (2018).
  38. Alzheev, A. V., Kochkarov, R. A., “Comparative analysis of ARIMA and LSTM predictive models: Evidence from Russian stocks”, Finance: Theory and Practice, 24(1), 14-23, (2020).
  39. Elsaraiti, M., Merabet, A., “A comparative analysis of the ARIMA and LSTM predictive models and their effectiveness for predicting wind speed”, Energies, 14(20), 6782, (2021).
  40. Wu, H., Chen, S., Ding, Y., “Comparison of ARIMA and LSTM for Stock Price Prediction”, Financial Engineering and Risk Management, 6(1), 1-7, (2023).
  41. Hamiane, S., Ghanou, Y., Khalifi, H., Telmem, M., “Comparative analysis of LSTM, ARIMA, and hybrid models for forecasting future GDP”, Journal Homepage: http://iieta. org/journals/isi, 29(3), 853-861, (2024).
  42. Nensi, A. I. E., Al Maida, M., Notodiputro, K. A., Angraini, Y., Mualifah, L. N. A., “Performance Analysis of ARIMA, LSTM, and Hybrid ARIMA-LSTM in Forecasting the Composite Stock Price Index”, CAUCHY: Jurnal Matematika Murni dan Aplikasi, 10(2), 588-604, (2025).
  43. Köse, N., Gür, Y. E., Ünal, E., “Deep Learning and Machine Learning Insights Into the Global Economic Drivers of the Bitcoin Price”, Journal of Forecasting, (2025).
  44. Ouliaris, S., Pagan, A., Restrepo, J., “Quantitative macroeconomic modeling with structural vector autoregressions–an EViews implementation”, IHS Global, 13, (2016).
  45. Startz, R., “EViews Illustrated”, University of California: Santa Barbara, CA, USA, (2019).
  46. Dahl, G., Ranzato, M. A., Mohamed, A. R., Hinton, G. E., “Phone recognition with the mean-covariance restricted Boltzmann machine”, Advances in Neural Information Processing Systems, 23, (2010).
  47. Bordes, A., Glorot, X., Weston, J., Bengio, Y., “Joint learning of words and meaning representations for open-text semantic parsing”, Artificial Intelligence and Statistics, 127-135, (2012).
  48. Krizhevsky, A., Sutskever, I., Hinton, G. E., “ImageNet classification with deep convolutional neural networks”, Communications of the ACM, 60(6), 84-90, (2017).
  49. Zhang, Q., Yang, L. T., Chen, Z., Li, P., “A survey on deep learning for big data”, Information Fusion, 42, 146-157”, (2018).
  50. Sherstinsky, A., “Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network”, Physica D: Nonlinear Phenomena, 404, 132306, (2020).
  51. Yang, S., Yu, X., Zhou, Y., “LSTM and GRU Neural Network Performance Comparison Study: Taking Yelp Review Dataset as an Example”, International Workshop on Electronic Communication and Artificial Intelligence, Shanghai, China, (2020).
  52. https://thorirmar.com/post/insight_into_lstm. Access date: 30.12.2025
  53. Dinardo, J., Johnston, J., “Econometric Methods”, McGraw-Hill, (1996).
  54. Fama, E. F., “Random walks in stock market prices”, Financial Analysts Journal, 51(1), 75-80, (1965).
  55. Fama, E. F., “Efficient capital markets: A review of theory and empirical work”, The Journal of Finance, 25(2), 383-417, (1970).
  56. Meese, R. A., Rogoff, K., “Empirical exchange rate models of the seventies: Do they fit out of sample?”, Journal of international economics, 14(1-2), 3-24, (1983).
  57. Makridakis, S., Andersen, A., Carbone, R., Fildes, R., Hibon, M., Lewandowski, R., Winkler, R., “The accuracy of extrapolation (time series) methods: Results of a forecasting competition”, Journal of Forecasting, 1(2), 111-153, (1982).
  58. Chatfield, C., “Apples, oranges and mean square error”, International Journal of Forecasting, 4(4), 515-518, (1988).
  59. Armstrong, J. S., Collopy, F., “Error measures for generalizing about forecasting methods: Empirical comparisons”, International Journal of Forecasting, 8(1), 69-80, (1992).
  60. Armstrong, J. S., “Principles of Forecasting: A Handbook for Researchers and Practitioners”, 443-472, (2001).
  61. Fildes, R., “The evaluation of extrapolative forecasting methods”, International Journal of Forecasting, 8(1), 81-98, (1993).
  62. Dickey, D. A., Fuller, W. A., “Likelihood ratio statistics for autoregressive time series with a unit root”, Econometrica: Journal of the Econometric Society, 1057-1072, (1981).
  63. Gelman, A., Carlin, J. B., Stern, H. S., Dunson, D. B., Vehtari, A., Rubin, D. B., “Bayesian Data Analysis”, 3rd ed., Chapman and Hall/CRC, (2013).
  64. Milà, C., Mateu, J., Pebesma, E., Meyer, H., “Nearest neighbour distance matching Leave‐One‐Out Cross‐Validation for map validation”, Methods in Ecology and Evolution, 13(6), 1304-1316, (2022).
  65. Makridakis, S., Hibon, M., “The M3-Competition: results, conclusions and implications”, International journal of forecasting, 16(4), 451-476, (2000).
  66. Green, K. C., Armstrong, J. S., “Simple versus complex forecasting: The evidence”, Journal of Business Research, 68(8), 1678–1685, (2015).
  67. Xiao D., Ketcha M.D., “Deep Speech 2: End-to-end speech recognition in English and mandarin”, Journal of Heterocyclic Chemistry, 32(2), 499–503, (1995).